Using hierarchical hidden Markov models to perform sequence-based classification of protein structure

Jian Yu Shi, Yan Ning Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

In the post-genome era, as an essential alternative of experimental method, the computational method is becoming popular. The prediction of protein structural class from protein sequence becomes one of research's concerns because the knowledge of protein structural class can simplify and accelerate in the computational determination of the spatial structure of a newly identified protein. As one of sequence-based approaches, hidden Markov model(HMM) provides a convenient and effective tool to analyze and classify protein sequence. In this paper, we firstly present the 6-state HMM which holds fewer states, clear transition groups and fewer model parameters. Then, by considering the knowledge of hierarchical structure of protein based on the 6-state HMM, we further propose the hierarchical hidden Markov model (HHMM) which has not only clear biological meaning, but also fewer number of transitions. Finally, the experimental comparison of various methods demonstrates that both the HHMM and the 6-state HMM outperform other method.

Original languageEnglish
Title of host publicationICSP2010 - 2010 IEEE 10th International Conference on Signal Processing, Proceedings
Pages1789-1792
Number of pages4
DOIs
StatePublished - 2010
Event2010 IEEE 10th International Conference on Signal Processing, ICSP2010 - Beijing, China
Duration: 24 Oct 201028 Oct 2010

Publication series

NameInternational Conference on Signal Processing Proceedings, ICSP

Conference

Conference2010 IEEE 10th International Conference on Signal Processing, ICSP2010
Country/TerritoryChina
CityBeijing
Period24/10/1028/10/10

Keywords

  • Classification
  • Hidden Markov model
  • Hierarchical hidden Markov model
  • Protein sequence

Fingerprint

Dive into the research topics of 'Using hierarchical hidden Markov models to perform sequence-based classification of protein structure'. Together they form a unique fingerprint.

Cite this